← 트렌딩
Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.
dflash-mlx
github.com
Lossless DFlash speculative decoding for MLX on Apple Silicon
오픈소스
설치·연결
공식 MCP Registry, Homebrew, npm, PyPI, crates.io에서 저장소나 도메인으로 맞춰 하루 한 번 가져옵니다.
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
dflash
DFlash: Block Diffusion for Flash Speculative Decoding
speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
mlx
MLX: An array framework for Apple silicon
mlx-dspark
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
SpecForge
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.